Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4944 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4669. Min Range: -5.4669
Max Act: 5.4356. Min Act: -0.1700
Data Index: 1771489 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4669. Min Range: -5.4669
Max Act: 5.4669. Min Act: -0.1700
Data Index: 3986869 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4669. Min Range: -5.4669
Max Act: 5.4044. Min Act: -0.1700
Data Index: 1618897 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4669. Min Range: -5.4669
Max Act: 5.3731. Min Act: -0.1700
Data Index: 6839585 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4669. Min Range: -5.4669
Max Act: 5.3419. Min Act: -0.1700
Data Index: 4969847 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4669. Min Range: -5.4669
Max Act: 5.3419. Min Act: -0.1700
Data Index: 958109 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4669. Min Range: -5.4669
Max Act: 5.3419. Min Act: -0.1700
Data Index: 5299796 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4669. Min Range: -5.4669
Max Act: 5.3419. Min Act: -0.1700
Data Index: 5191299 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4669. Min Range: -5.4669
Max Act: 5.3106. Min Act: -0.1700
Data Index: 7805391 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4669. Min Range: -5.4669
Max Act: 5.2794. Min Act: -0.1700
Data Index: 8622150 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4669. Min Range: -5.4669
Max Act: 5.3419. Min Act: -0.1700
Data Index: 5476286 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4669. Min Range: -5.4669
Max Act: 5.2794. Min Act: -0.1700
Data Index: 3577954 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4669. Min Range: -5.4669
Max Act: 5.2481. Min Act: -0.1700
Data Index: 5780926 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4669. Min Range: -5.4669
Max Act: 5.3106. Min Act: -0.1700
Data Index: 95180 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4669. Min Range: -5.4669
Max Act: 5.2794. Min Act: -0.1699
Data Index: 281032 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4669. Min Range: -5.4669
Max Act: 5.2794. Min Act: -0.1700
Data Index: 4961655 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4669. Min Range: -5.4669
Max Act: 5.2794. Min Act: -0.1700
Data Index: 7649856 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4669. Min Range: -5.4669
Max Act: 5.2481. Min Act: -0.1700
Data Index: 225410 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4669. Min Range: -5.4669
Max Act: 5.2481. Min Act: -0.1700
Data Index: 1250813 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4669. Min Range: -5.4669
Max Act: 5.2169. Min Act: -0.1700
Data Index: 6949971 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19